Processing contrast-enhanced ultrasound images of lesions

Abstract

According to one aspect, a computer-implemented method (300) of processing a contrast-enhanced ultrasound image of a lesion is provided. The method comprises: comparing (302) attributes of a lesion described in a contrast-enhanced ultrasound report of a contrast-enhanced ultrasound image to a reference, thereby determining an inconsistency in the contrast-enhanced ultrasound report; and sending a message to a user equipment (304) to cause the user equipment to provide an alert related to the inconsistency, thereby providing feedback.

Description

Technical Field

[0001] The disclosure herein relates to processing contrast-enhanced ultrasound images of lesions.More particularly, but not exclusively, embodiments herein relate to providing warnings related to inconsistencies in contrast-enhanced ultrasound reports. Background Art

[0002] Liver cancer is one of the leading causes of cancer death worldwide. Although MRI (magnetic resonance imaging) and CT (computed tomography) are both recommended medical imaging methods for diagnosing liver cancer, both CT and MRI require high costs and complex instruments. Therefore, contrast-enhanced ultrasound (CEUS) has become a commonly used imaging modality for the diagnosis of liver lesions due to its low price, rapidity, and non-invasive imaging.

[0003] During the diagnosis of liver tumors using CEUS images, the physician injects contrast agent into the patient's blood vessels. After the contrast agent is injected, the clinician observes and records several CEUS cycles as the contrast agent flows through the lesion (or other anatomical features of interest) during the procedure. Compared with traditional ultrasound modalities, CEUS is more complex and has spatial and temporal information corresponding to the contrast period.

[0004] During the presentation, clinicians write their observations and features, along with their diagnostic conclusions, in a report called a CEUS report. The Liver Imaging Reporting and Data System (LI-RADS), a classification system for liver lesions, can help standardize observed features and provide expert consensus for them. Elsayes et al. describe LI-RADS in detail in the paper titled: “LI-RADS: a conceptual and historical review from its beginning to its recent integration into AASLD clinical practice guidance.” J Hepatocell Carcinoma. 2019;6:49–69. Published online February 5, 2019. doi: 10.2147 / JHC.S186239.

[0005] US2021366106A1 discloses a retrospective differential marking system and method, which can generate consensus data by performing a consensus function on automatic evaluation data and manual evaluation data. US20050251014A1 discloses a method and system for quality assurance of lesion marking to reduce intra-observer and inter-observer inconsistency. Summary of the invention

[0006] As mentioned above, the diagnosis of contrast-enhanced ultrasound (CEUS) images is usually based on the interpretation of the image or circulation, for example, by the physician extracting important features. Guidelines such as CEUS LI-RADS, which is a classification system for liver lesions, help provide expert consensus on these features. During the report, clinicians usually write down their observations and features before reaching a diagnostic conclusion. These observations are usually included in the CEUS report.

[0007] It is an object of the present disclosure to provide an improved reporting mechanism for CEUS examinations. The invention is defined by the independent claims. The dependent claims define advantageous embodiments.

[0008] According to a first aspect, a computer-implemented method for processing a contrast-enhanced ultrasound image of a lesion is provided. The method comprises: comparing the attributes of the lesion described in a contrast-enhanced ultrasound report of the contrast-enhanced ultrasound image with a reference, thereby determining an inconsistency in the contrast-enhanced ultrasound report; and sending a message to a user device so that the user device provides a warning related to the inconsistency, thereby providing feedback. The determined inconsistency includes one of the following: (a) an inconsistency determined between at least two different attributes of the lesion and a reference including a predefined relationship, and (b) an inconsistency of the attribute of the lesion determined between the attribute of the lesion and a reference including an attribute of the lesion measured in a second ultrasound image obtained using a modality different from the contrast-enhanced ultrasound image.

[0009] According to a second aspect, a device for processing a contrast-enhanced ultrasound image of a lesion is provided. The device comprises: a memory including instruction data representing a set of instructions; and a processor configured to communicate with the memory and execute the set of instructions. When the set of instructions is executed by the processor, the processor executes the method according to the first aspect.

[0010] According to a third aspect, there is an ultrasound imaging system comprising the apparatus according to the second aspect. The apparatus further comprises a transducer; and the method is performed during ultrasound contrast examination to provide real-time feedback.

[0011] According to a fourth aspect, there is provided a computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that when run by a suitable computer or processor, the computer or processor is caused to perform the method according to the first aspect.

[0012] Thus, in this way, inconsistencies in CEUS reports can be determined and warnings issued so that clinicians can review these inconsistencies and correct the inconsistencies or obtain new CEUS images. Thus, an improved CEUS imaging process is provided, improving the quality of CEUS images and their analysis. Improved CEUS imaging and analysis lead to improved patient outcomes. Traditionally, consistency, consensus or discrepancy checks focus on resolving differences between automated and manual measurements or between manual measurements made by different users or between different scans. The present application proposes a consistency check method specifically for CEUS imaging. Using the proposed method, inconsistencies between different but related attributes or between attributes obtained from CEUS and another different ultrasound imaging method can be determined and warned.

[0013] These and other aspects will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Exemplary embodiments will now be described, by way of example only, with reference to the accompanying drawings, in which:

[0015] Figure 1 An apparatus according to some embodiments herein is shown;

[0016] Figure 2 is an ultrasound imaging system according to some embodiments herein;

[0017] Figure 3 Methods according to some embodiments herein are shown; and

[0018] Figure 4 An example flow chart in ultrasound imaging is shown. DETAILED DESCRIPTION

[0019] As described above, the diagnostic conclusions of contrast-enhanced ultrasound (CEUS) examinations are typically recorded in CEUS reports. Factors such as time pressure may cause errors in such reports. For example, there may be inconsistencies in the report, such as mutually incompatible information. This may lead to misdiagnosis, resulting in reduced quality of care and reduced patient outcomes. The disclosure herein is intended to improve the quality of reports in terms of self-consistency and to issue warnings in a manner that a clinician or sonographer can take action so that inconsistencies can be checked and corrected, and / or additional information can be obtained. Three main situations are considered: 1) consistency of lesion size between B-mode and CEUS; 2) consistency between different but related features; 3) consistency between features and diagnostic conclusions. The disclosure herein is able to detect self-inconsistencies in these scenarios and ensure that clinical users act accordingly.

[0020] Now go to Figure 1 In some embodiments, there is an apparatus 100 for processing CEUS images of lesions. Generally speaking, the apparatus may form part of a computer apparatus or system (e.g., a laptop, desktop computer, or other computing device). In some embodiments, the apparatus 100 may form part of a distributed computing arrangement or cloud.

[0021] The apparatus includes a memory 104 and a processor 102 (e.g., a processing circuit or logic device), the memory including instruction data representing a set of instructions 106, and the processor is configured to communicate with the memory and execute the set of instructions. In general, the set of instructions, when executed by the processor, can cause the processor to perform any embodiment of the method 300 described above.

[0022] Embodiments of the apparatus 100 may be used to process a CEUS image of a lesion. More specifically, when the processor executes the set of instructions 106, the processor is caused to: compare the properties of the lesion described in the CEUS report of the CEUS image with a reference, thereby determining inconsistencies in the CEUS report; and send a message to a user device to cause the user device to provide a warning related to the inconsistency, thereby providing feedback.

[0023] The processor 102 may include one or more processors, processing units, multi-core processors, or modules, which are configured or programmed to control the device 100 in the manner described herein. In a specific implementation, the processor 102 may include multiple software and / or hardware modules, each of which is configured to perform or is used to perform a single or multiple steps of the method described herein. The processor 102 may include one or more processors, processing units, multi-core processors, and / or modules, which are configured or programmed to control the device 100 in the manner described herein. In some embodiments, for example, the processor 102 may include multiple (e.g., interoperable) processors, processing units, multi-core processors, and / or modules configured for distributed processing. Those skilled in the art will appreciate that such processors, processing units, multi-core processors, and / or modules may be located in different locations and may perform different steps and / or different parts of a single step of the method described herein.

[0024] The memory 104 is configured to store program codes that can be executed by the processor 102 to perform the methods described herein. Alternatively or additionally, one or more memories 104 can be external to the device 100 (i.e., separate or remote). For example, one or more memories 104 can be part of another device. The memory 104 can be used to store CEUS images, CEUS reports, and / or any other information or data received, calculated, or determined by the processor 102 of the device 100 or from any interface, memory, or device external to the device 100. The processor 102 can be configured to control the memory 104 to store CEUS images, CEUS reports, and / or any other information or data.

[0025] In some embodiments, the memory 104 may include multiple sub-memories, each of which can store one instruction data. For example, at least one sub-memory can store instruction data representing at least one instruction in the set of instructions, and at least one other sub-memory can store instruction data representing at least one other instruction in the set of instructions.

[0026] It should be understood that Figure 1 Only components necessary to illustrate this aspect of the present disclosure are shown, and in actual implementation, the device 100 may include components additional to those shown. For example, the device 100 may also include a display. The display may include, for example, a computer screen and / or a screen on a mobile phone or tablet computer. The device may also include a user input device, such as a keyboard, mouse or other input device, which enables a user to interact with the device, for example, to provide initial input parameters to be used in the methods described herein. The device 100 may include a battery or other power source for powering the device 100 or a device for connecting the device 100 to a mains power source.

[0027] In some embodiments, the device 100 is incorporated into an ultrasound (US) imaging system. For example, the ultrasound imaging system may include the device 100 and a display for displaying a warning.

[0028] The ultrasound imaging system may also include other components, such as components associated with acquiring and processing ultrasound image data. Figure 2An example ultrasound imaging system 200 is shown in FIG. The ultrasound system 200 includes an array transducer probe 4 having a transducer array 6 for transmitting ultrasound and receiving echo information. The transducer array 6 may include a CMUT (capacitive micromachined ultrasonic transducer) transducer; a piezoelectric transducer made of a material such as PZT (lead zirconate titanate) or PVDF (polyvinylidene fluoride); or any other suitable transducer technology. In this example, the transducer array 6 is a two-dimensional array of transducers 8 capable of scanning a 2D plane or a three-dimensional volume of a region of interest. In another example, the transducer array may be a 1D array.

[0029] The transducer array 6 may be coupled to a microbeamformer 12 that controls the reception of signals by the transducer elements. As described in U.S. Pat. Nos. 5,997,479 (Savord et al.), 6,013,032 (Savord), and 6,623,432 (Powers et al.), a microbeamformer is capable of at least partially beamforming signals received by sub-arrays (generally referred to as "groups" or "patches") of transducers.

[0030] In an alternative embodiment, instead of the microbeamformer 12, the transducer array may be provided by a main system beamformer ( Figure 2 ) directly operated.

[0031] The system 200 may also include a transmit / receive (T / R) switch 16 to which the microbeamformer 12 may be coupled and which switches the array between transmit and receive modes. Transmission of ultrasound beams from the transducer array 6 is directed by a transducer controller 18 coupled to the microbeamformer and a main transmit beamformer (not shown) via the T / R switch 16, which may receive input from a user operating a user interface or control panel 38. The controller 18 may include transmit circuitry arranged to drive the transducer elements of the array 6 (directly or via the microbeamformer) during the transmit mode.

[0032] Note that in alternative embodiments, the transducer array is operated directly by the main system beamformer rather than the microbeamformer 12, and the T / R switch 16 may protect the main beamformer 20 from high energy transmit signals.

[0033] In a typical line-by-line imaging sequence, the beamforming system within the probe may operate as follows. During transmit, the beamformer (which may be a microbeamformer or a main system beamformer depending on the implementation) activates a transducer array or a subaperture of a transducer array. A subaperture may be a one-dimensional line of transducers or a two-dimensional patch of transducers within a larger array. In transmit mode, the focusing and steering of the ultrasound beam produced by the array or a subaperture of the array is controlled as described below.

[0034] After receiving the backscattered echo signal from the object, the received signal is subjected to receive beamforming (described below) to align the received signal and, in the case of using a subaperture, shift the subaperture, for example, by one transducer element. The shifted subaperture is then activated and the process is repeated until all transducer elements of the transducer array are activated.

[0035] For each line (or sub-aperture), the total received signal used to form the line associated with the final ultrasound image will be the sum of the voltage signals measured by the transducer elements of the given sub-aperture during the receive period. After the beamforming process below, the resulting line signal is typically referred to as radio frequency (RF) data. Each line signal (RF data set) generated by the individual sub-apertures is then subjected to additional processing to generate the lines of the final ultrasound image. The change in the amplitude of the line signal over time will contribute to the change in brightness of the ultrasound image with depth, where high amplitude peaks will correspond to bright pixels (or sets of pixels) in the final image. Peaks that appear near the beginning of the line signal will represent echoes from shallow structures, while peaks that appear later in the line signal represent echoes from structures with increasing depth within the object.

[0036] One of the functions controlled by the transducer controller 18 is the direction in which the beam is steered and focused. The beam can be steered straight forward from the transducer array (perpendicular to the transducer array), or at a different angle for a wider field of view. The steering and focusing of the transmit beam can be controlled based on the transducer element actuation time.

[0037] In general ultrasound data acquisition two methods can be distinguished: plane wave imaging and "beam steering" imaging. The two methods differ in that beam forming is present in the transmit mode ("beam steering" imaging) and / or in the receive mode (plane wave imaging and "beam steering" imaging).

[0038] First, let's look at the focusing function. By activating all transducer elements simultaneously, the transducer array generates a plane wave that diverges when passing through the object. In this case, the beam of ultrasound waves remains unfocused. By introducing a position-dependent time delay into the activation of the transducer, the wavefront of the beam can be converged at a desired point, which is called the focal zone. The focal zone is defined as the point where the lateral beam width is less than half the transmit beam width. In this way, the lateral resolution of the final ultrasound image is improved.

[0039] For example, if the time delay is such that the transducer elements are activated in series starting with the outermost elements and ending at the center element(s) of the transducer array, a focal region will be formed at a given distance from the probe, in line with the center element(s). The distance of the focal region from the probe will vary depending on the time delay between each subsequent round of transducer element activation. After the beam passes through the focal region, it will begin to diverge, forming a far-field imaging region. It should be noted that for a focal region located close to the transducer array, the ultrasound beam will diverge rapidly in the far field, resulting in beam width artifacts in the final image. Typically, the near field located between the transducer array and the focal region displays little detail due to the large overlap in the ultrasound beam. Therefore, changing the position of the focal region can result in significant changes in the quality of the final image.

[0040] It should be noted that in transmit mode, only one focus may be defined unless the ultrasound image is divided into multiple focal regions (each focal region may have a different transmit focus).

[0041] Additionally, when echo signals are received from inside the object, the inverse of the above process can be performed to perform receive focusing. In other words, the incoming signal can be received by the transducer elements and undergo an electronic time delay before being passed into the system for signal processing. The simplest example is called delay and sum beamforming. The receive focus of the transducer array can be adjusted dynamically based on time.

[0042] Turning now to the function of beam steering, by correctly applying time delays to the transducer elements, a desired angle can be imparted on the ultrasound beam as it leaves the transducer array. For example, by activating the transducers on a first side of the transducer array, and then activating the remaining transducers in a sequence ending on the opposite side of the array, the wavefront of the beam will be tilted toward the second side. The size of the steering angle relative to the normal to the transducer array depends on the size of the time delay between subsequent transducer element activations.

[0043] Furthermore, the steered beam can be focused, where the total time delay applied to each transducer element is the sum of the focusing and steering time delays. In this case, the transducer array is called a phased array.

[0044] In the event that the CMUT transducers require a DC bias for activation, the transducer controller 18 may be coupled to control the transducer array's DC bias controller 45. The DC bias controller 45 sets the bias voltage(s) applied to the CMUT transducer elements.

[0045] For each transducer element of the transducer array, an analog ultrasound signal (commonly referred to as channel data) enters the system through a receive channel. In the receive channel, a partially beamformed signal is generated from the channel data by a microbeamformer 12 and is then transmitted to a main receive beamformer 20 where the partially beamformed signals from the individual transducer slices are combined into a fully beamformed signal, referred to as radio frequency (RF) data. The beamforming performed at each stage may be performed as described above, or additional functionality may be included. For example, the main beamformer 20 may have 128 channels, each of which receives partially beamformed signals from tens or hundreds of transducer elements. In this way, the signals received by thousands of transducers of the transducer array may effectively contribute to a single beamformed signal.

[0046] The beamformed received signals are coupled to a signal processor 22. The signal processor 22 can process the received echo signals in various ways, such as: bandpass filtering; decimation; I and Q component separation; and harmonic signal separation for separating linear and nonlinear signals to identify nonlinear (higher harmonics of the fundamental frequency) echo signals returning from tissue and microbubbles. The processor can also perform signal enhancements such as ripple reduction, signal compounding, and noise cancellation. The bandpass filter in the signal processor can be a tracking filter, in which its passband slides from a higher frequency band to a lower frequency band as the echo signal is received from an increasing depth, thereby rejecting noise at higher frequencies from greater depths, which is generally devoid of anatomical information.

[0047] The beamformers for transmission and for reception are implemented in different hardware and may have different functions. Of course, the receiver beamformer is designed to take into account the characteristics of the transmit beamformer. Figure 2 Only the receiver beamformers 12, 20 are shown in FIG. In the whole system there will also be a transmit chain with a transmit microbeamformer and a main transmit beamformer.

[0048] The function of the microbeamformer 12 is to provide initial combining of the signals in order to reduce the number of analog signal paths. This is typically performed in the analog domain.

[0049] Final beamforming is done in the main beamformer 20, typically after digitization.

[0050] The transmit and receive channels use the same transducer array with fixed frequency bands6. However, the bandwidth occupied by the transmit pulses can vary depending on the transmit beamforming used. The receive channel can capture the entire transducer bandwidth (this is the classical approach) or, by using bandpass processing, it can extract only the bandwidth containing the desired information (e.g. harmonics of the main harmonic).

[0051] The RF signal can then be coupled to a B-mode (i.e., brightness mode or 2D imaging mode) processor 26 and a Doppler processor 28. The B-mode processor 26 performs amplitude detection on the received ultrasound signal to image structures (e.g., organ tissue and blood vessels) in the body. In the case of line-by-line imaging, each line (beam) is represented by an associated RF signal, whose amplitude is used to generate a brightness value to be assigned to a pixel in the B-mode image. The exact position of the pixel within the image is determined by the position of the associated amplitude measurement along the RF signal and the number of lines (beams) of the RF signal. B-mode images of such structures can be formed in harmonic or fundamental image modes or a combination of the two, as described in US 6283919 (Roundhill et al.) and US 6458083 (Jago et al.). The Doppler processor 28 can process temporally discrete signals originating from tissue motion and blood flow for detecting moving matter, such as the flow of blood cells in the image field. The Doppler processor 28 typically includes a wall filter having parameters set to pass or reject echoes returning from selected types of material in the body.

[0052] The structure and motion signals generated by the B-mode and Doppler processors are coupled to the scan converter 32 and the multi-planar reformatter 44. The scan converter 32 arranges the echo signals in the desired image format according to the spatial relationship in which the echo signals are received. In other words, the role of the scan converter is to convert the RF data from a cylindrical coordinate system to a Cartesian coordinate system suitable for displaying an ultrasound image on the image display 40. In the case of B-mode imaging, the brightness of a pixel at a given coordinate is proportional to the amplitude of the RF signal received from that location. For example, the scan converter can arrange the echo signals into a two-dimensional (2D) sector-shaped format, or a pyramidal three-dimensional (3D) image. The scan converter can superimpose on the B-mode structural image the colors corresponding to the motion of various points in the image field, where the Doppler estimated velocity can produce a given color. The combined B-mode structural image and color Doppler image can describe the tissue motion and blood flow within the structural image field. The multi-planar reformatter converts the echoes received from points in a common plane in a volumetric region of the body into an ultrasound image of that plane, as described in US 6443896 (Detmer). The volume renderer 42 converts the echo signals of the 3D data set into a projected 3D image as seen from a given reference point, as described in US 6530885 (Entrekin et al.).

[0053] The 2D or 3D images are coupled from the scan converter 82, the multi-planar reformatter 44, and the volume renderer 42 to the image processor 30 for further enhancement, buffering, and temporary storage for display on the image display 40. The imaging processor may be adapted to remove certain imaging artifacts from the final ultrasound image, such as, for example: acoustic shadowing, e.g. caused by strong attenuators or refraction; post-enhancement, e.g. caused by weak attenuators; reverberation artifacts, e.g., the close proximity of highly reflective tissue interfaces; etc. In addition, the image processor may be adapted to process certain ripple reduction functions to improve the contrast of the final ultrasound image.

[0054] In addition to being used for imaging, the blood flow values ​​generated by the Doppler processor 28 and the tissue structure information generated by the B-mode processor 26 are coupled to a quantification processor 34. The quantification processor can be used to make measurements in the images. The quantification processor can receive input from a user control panel 38.

[0055] The output data from the quantization processor is coupled to the graphics processor 36 for reproducing the measurement graphs and values ​​on the display 40 together with the image, and for outputting audio from the display device 40. The graphics processor 36 may also generate graphic overlays for display with the ultrasound image. These graphic overlays may include standard identification information, such as the patient name, date and time of the image, imaging parameters, etc. For these purposes, the graphics processor receives input from the user interface 38, such as the patient name. The user interface is also coupled to the transmit controller 18 to control the generation of ultrasound signals from the transducer array 6, and thus control the images generated by the transducer array and the ultrasound system. The transmit control function of the controller 18 is only one of the functions performed. The controller 18 also takes into account the operating mode (given by the user) and the corresponding required transmitter configuration and bandpass configuration in the receiver analog-to-digital converter. The controller 18 may be a state machine with fixed states.

[0056] A user interface may also be coupled to the multi-planar reformatter 44 to select and control planes of a plurality of multi-planar reformatted (MPR) images, which may be used to perform quantitative metrics in the image field of the MPR images.

[0057] It should be understood that Figure 2 The ultrasound image system illustrated in FIG. 1 is merely an example, and the ultrasound image system may include components different from those described above.

[0058] Go to Figure 3 , there is a computer-implemented method 300 for processing a contrast enhanced ultrasound (CEUS) image of a lesion. Embodiments of the method 300 may be performed, for example, by a device such as the device 100 or ultrasound imaging system 200 described above.

[0059] In brief, in a first step 302, the method 300 includes comparing the properties of the lesion described in the CEUS report of the CEUS image with the reference, thereby determining the inconsistency in the CEUS report. In a second step 304, the method includes sending a message to the user device so that the user device provides a warning related to the inconsistency, thereby providing feedback.

[0060] In more detail, a lesion may refer to an area of ​​any abnormal tissue in the body. For example, a lesion may be a tumor, such as a cancerous tumor. Examples of liver tumors include, but are not limited to, hepatocellular carcinoma (HCC), intrahepatic bile duct carcinoma (cholangiocarcinoma), hemangioendothelioma, and angiosarcoma. However, those skilled in the art will appreciate that these are merely examples, and that a lesion may be any type of lesion.

[0061] As mentioned above, to obtain CEUS images, the physician injects contrast media into the patient's blood vessels (intravenous injection). After the contrast media is injected, the clinician observes and records several CEUS cycles during the procedure as the contrast media flows over the lesion (or other anatomical features of interest). Compared to traditional ultrasound modalities, CEUS is more complex, with spatial and temporal information corresponding to different imaging phases.

[0062] CEUS imaging is described in more detail in the following article by Dietrich et al.: entitled “How to perform Contrast-Enhanced Ultrasound (CEUS)”; Ultrasound Int Open. 2018 Jan;4(1):E2–E15. Published online February 7, 2018. doi:10.1055 / s-0043-123931.

[0063] Dietrich's paper states that CEUS can record and evaluate the wash-in and wash-out phases of ultrasound contrast agents (UCA) in real time within a few minutes. This can provide dynamic visualization of different vascular phases when examining the liver. Due to the peculiarities of the liver's blood supply, three different phases have been defined: arterial phase (AP), portal venous phase (PVP), and late (sinusoidal) phase (LP).

[0064] A CEUS report is any report generated to contain data related to a CEUS image. For example, a CEUS report may include images, measurements, observations, annotations, or diagnoses made by a clinician or sonographer. It is noteworthy that the terms "physician," "clinician," "sonographer," and "user" are used interchangeably herein.

[0065] The CEUS report may include other measurements, such as those made or predicted by a diagnostic procedure. The diagnostic procedure may refer to a computer-assisted diagnostic procedure. The diagnostic procedure may use machine learning to generate one or more annotations of the CEUS image, and these annotations may be recorded in the CEUS report. For example, a machine learning model may be used to annotate a CEUS image with information (e.g., the presence / absence of a lesion, the location of a lesion, the size of a lesion, or other dimensional information).

[0066] In some embodiments, segmentation can be used to obtain shape / size information about lesions in CEUS images. Those skilled in the art will be familiar with segmentation methods, such as the model-based segmentation described in the following paper by d Ecabert, O. et al.: 2008 entitled "Automatic Model-Based Segmentation of the Heart in CT Images"; IEEE Trans. Med. Imaging 27(9), 1189–1201. Another segmentation method uses a machine learning (ML) model to convert an image into multiple component shapes (e.g., block shapes or block volumes) based on similar pixel / voxel values ​​and image gradients. This is described, for example, in the paper entitled "Fully Convolutional Networks for Semantic Segmentation" by Long et al.

[0067] CEUS reports can be in any format, such as Microsoft TM WORD document, Portable Document Format (pdf) document, Microsoft TM PowerPoint document, Microsoft TM Excel document (xlxs), text file (txt), Extensible Markup Language (XML), Hypertext Markup Language (HTML), Rich Text Format (RTF), Open Document Text Document (ODT), JPEG image (JPG), Portable Network Graphics image (PNG), or any other document format.

[0068] In step 302 , as described above, method 300 includes comparing properties of a lesion described in a CEUS report of a CEUS image with a reference to thereby determine inconsistencies in the CEUS report.

[0069] In some embodiments, the attributes of the lesion include contrast phase information from a CEUS report. The reference may then include predefining relationships between different contrast phases based on contrast phase perfusion physiology, and if the contrast phase information from the CEUS report is inconsistent with the predefined relationship, an inconsistency may be determined. For example, some phases occur in a specific order, reflecting different phases as contrast agent flows through the lesion. Thus, the predefined relationship may indicate the order in which different contrast phases should be recorded in the report.

[0070] Thus, in some embodiments, if the angiography sessions are not recorded in chronological order in the CEUS report, or are recorded in a physiologically implausible combination, then an inconsistency is determined to exist.

[0071] The features in the report can be divided into three groups: time, degree of enhancement (DoE), and pattern of enhancement. The group of time features includes arterial phase (AP) start time, peak time, high enhancement start time, isoenhancement start time, and low enhancement start time. The group of degree of enhancement includes AP DoE, portal venous phase (PVP) DoE, late (LP) DoE, early clearance, and degree of clearance. These two groups are related to each other because the features in the second group are all time-related. For example, AP DoE means the DoE of AP, where AP is defined from the AP start time to approximately 45 seconds. Therefore, if the time features and DoE are recorded in a physiologically impossible combination or in a manner that is opposite to the way the respective features are defined, an inconsistency can be determined. In other words, if the time features and DoE are recorded in a manner that is opposite to the inherent relationship between the time features and DoE, an inconsistency can be determined.

[0072] Some examples of predefined relationships are as follows:

[0073] 1) Due to the perfusion physiology of contrast media, the arterial phase (AP) start time is always earlier than the peak time, so if someone records the AP start time greater than the peak time, there is an inconsistency.

[0074] 2) If the degree of enhancement (DoE) of the lesion during AP is isoenhancement, then since the contrast medium will not be reperfused during PVP and LP, the lesion should only appear isoenhanced or hypoenhanced during PVP and / or LP. Therefore, if someone records an AP DoE of isoenhancement, a PVP DoE of hyperenhancement, and / or a LP DoE of hyperenhancement, there is an inconsistency.

[0075] 3) If the PVP DoE of a lesion is isoenhanced, then due to tissue perfusion physiology, the LP DoE can only be isoenhanced or hypoenhanced, so if someone records the LP DoE as hyperenhanced, there is an inconsistency within the lesion.

[0076] 4) The degree of enhancement (DoE) of the lesion by PVP DoE is mainly determined by the frames around 120s after contrast injection (from the start of contrast introduction). That is, if the lesion is isoenhanced in these frames, the PVP DoE is also isoenhanced. The characteristics of the PVP DoE are related to the degree of clearing at 120s. If the PVP DoE is isoenhanced, the degree of clearing must be "none" because the lesion has not been cleared. Therefore, if the degree of clearing is recorded as "significant" or "mild", there is inconsistency.

[0077] 5) If the lesion shows "early washout", this means that the DoE of the lesion 60 seconds ago is hypoenhanced, so the PVP DoE and LP DoE can only be hypoenhanced, and the washout cannot be "none". Therefore, if a lesion is recorded as "early washout", and the PVP DoE and / or LP DoE are not hypoenhanced, and / or the washout is "none", there is an inconsistency.

[0078] In other words, the predefined relationship between different contrast phases may indicate that: the start of AP should be before peak contrast; if the DoE of the lesion during AP is isoenhancement, the lesion should appear isoenhancement or hypoenhancement during PVP and / or LP; if the PVP DoE of the lesion is isoenhancement, the LP DoE should be isoenhancement or hypoenhancement; if the PVP DoE is isoenhancement, the degree of washout should be zero; and / or if the lesion exhibits early washout, the PVP DoE and LP DoE should only be hypoenhancement and the degree of washout should be greater than none (e.g., non-zero).

[0079] It should be understood that these are merely examples, and that other attributes and other predefined relationships may be used as well. In general, any inconsistencies that may be contrary to the physiology of contrast agent perfusion should be taken into account.

[0080] In an example embodiment, step 302 may be implemented according to the following pseudo code:

[0081]

[0082]

[0083] Turning now to other embodiments, in some embodiments, a size consistency check is performed. In a CEUS examination, the lesion size is often measured multiple times, for example in a B-mode image and a CEUS image. There is a risk that the lesion size in these two measurements is inconsistent, especially when there is more than 1 lesion in the image. Therefore, if the lesion size in the CEUS image is different from the lesion size measured in the B-mode image, and the difference exceeds a certain threshold, the inconsistency in the lesion size may be highlighted.

[0084] Therefore, in some embodiments, in step 302, the reference includes an attribute of a lesion measured in a second ultrasound image obtained using a modality different from the CEUS image. The attribute of the lesion described in the CEUS report is a geometric attribute of the lesion measured in the CEUS image, and the reference is a value of the same geometric attribute measured in the second ultrasound image. If the value of the geometric attribute of the lesion measured in the CEUS image differs from the value of the geometric attribute of the lesion measured in the second ultrasound image by more than a threshold difference, it can be determined that there is an inconsistency. As described above, the second ultrasound image can be a B-mode ultrasound image.

[0085] The geometric attributes may include the size, radius, diameter, area or perimeter of the lesion. However, these are merely examples and any geometric or shape attribute may be measured between the CEUS image and the second ultrasound image. The threshold difference may be set empirically, for example based on the relative size distribution between a CEUS image and a corresponding image of the same type as the second image measured for a representative population.

[0086] In this way, measurement differences between the CEUS image and the second image may be highlighted.

[0087] Turning now to other embodiments, in some embodiments, the diagnosis or other derived quantities may be checked in the CEUS report. For example, a field (eg, a feature or parameter value) in the CEUS report may be checked for consistency with the diagnosis in the medical guidelines.

[0088] Examples of medical guidelines include, but are not limited to, the guidelines described in the following papers: Chen, M., Yan, K., Dai, Y., Wu, W., Xu, H., Yang, W., ... Yu, X. (2013). "Liver contrast-enhanced ultrasound application guidelines" (China, updated 2012). Chin. J. Ultrasonogr., 22 (8), 696-722; Claudon, M., Dietrich, CF, Choi, BI, Cosgrove, DO, Kudo, M., CP,...Chaubal,NG(2013).Guidelines and good clinical practice recommendations for contrast enhanced ultrasound(CEUS) in the liver–update 2012.Ultraschall inder Medizin-European Journal of Ultrasound,34(01),11-29;Kono,Y.,Lyshchik,A.,Cosgrove,D.,Dietrich,CF,Jang,HJ,Kim,TK,...Kambadakone,A.(2017).Contrastenhanced ultrasound(CEUS)liver imaging reporting and data system the official version by the American College of radiology (ACR). Ultraschall inder Medizin - European Journal of Ultrasound, 38(01), 85-86. However, those skilled in the art will appreciate that these are merely examples and that other medical guidelines may be used as well.

[0089] For example, a medical guideline may provide (e.g., indicate or suggest) a diagnosis based on a given set of feature values ​​(presence or observation). If the clinician arrives at a diagnosis that is not recommended by the medical guideline for a given set of parameter values ​​in the CEUS report or is inconsistent with the medical guideline, it may be highlighted as inconsistent. Thus, the information in the CEUS report may be compared with the medical guideline to check for mutual consistency.

[0090] In general, the reference attributes can be obtained from medical guidelines. In some embodiments, user input indicating a particular medical guideline to be used can be received. In other words, the user can indicate a guideline for consistency checking. In such embodiments, the reference attributes can be obtained from the indicated medical guideline.

[0091] The reference attribute may be related to the diagnosis in the CEUS report. Therefore, if the attribute in the CEUS report is not compatible with the reference attribute in the medical guideline, it can be determined that an inconsistency exists for the diagnosis in the CEUS report. Therefore, in this way, the method 300 can be used to determine whether the attribute in the CEUS report is inconsistent with the diagnosis in the CEUS report (e.g., by comparing with the medical guideline).

[0092] Back to Figure 3 In step 304, the method includes sending a message to the user device so that the user device provides a warning related to the inconsistency to provide feedback.

[0093] The user device may be, for example, a display (eg, a computer monitor), a warning light, or any other device that may be used to provide a warning to a user.

[0094] The warning may be any type of warning. For example, a visual warning (such as a message on a display), a tactile warning (such as a vibration of a user input device (e.g., a mouse or similar device)), or an audio warning (such as a beep or a computer-generated audio message). The warning may highlight that an inconsistency exists. The warning may indicate that one or more parts of the CEUS report are inconsistent. The warning may indicate that a repeat CEUS scan is needed.

[0095] In another example, when the device detects an inconsistency in lesion size, characteristics, or diagnosis, the device may request that the user review and / or confirm the inconsistent fields in the CEUS report.

[0096] In some embodiments, the method 300 is performed in real time, such as during a CEUS examination, and / or when a sonographer creates a CEUS report. In such an example, an alert may suggest in real time that a new CEUS scan be performed due to an inconsistency. In this way, the method 300 may be used in real time to indicate to the sonographer that further scans may be required, and to prompt the sonographer to collect the necessary information to make an accurate diagnosis, thereby improving the diagnosis, thereby leading to improved patient care and improved patient outcomes.

[0097] The feedback may include, for example, an indication of an inconsistency, an indication that a measurement should be repeated, an indication of one or more fields in a review report, an indication that a repeat scan may be needed, or any other feedback to the user.

[0098] It should be understood that the warnings noted above are merely examples, and that other warnings and other types of feedback are equally possible as a result of method 300 .

[0099] Method 300 can be triggered in a variety of ways, for example, in some embodiments, after the CEUS examination, a report generation user interface (UI) can be displayed to the user. This can be initiated by the user, for example, the user can confirm that they want to enter the report step. Functions related to the diagnosis may be shown in the user interface. In an embodiment where the user selects a guideline to compare with in step 302, the UI can provide the user with a list of guidelines so that they can select the guideline they want to reference / use in their own consistency check on the diagnosis.

[0100] Typically, the method 300 may be triggered, for example, when the clinical user confirms that they have finished providing the manual input. Thus, the apparatus may use the method 300 to check the consistency of the CEUS report.

[0101] Therefore, a CEUS reporting system is provided which can perform an automatic quality check on self-consistency in feature interpretation, diagnosis and lesion size. The CEUS reporting system can provide a warning to the user when self-consistency is detected.

[0102] Now go to Figure 4 , which shows an example embodiment of a method 400 according to some embodiments herein. In this embodiment, in step 402, a B-mode scan is performed on the lesion, from which a lesion size measurement is performed. In step 404, a CEUS scan is performed. In step 406, the size of the lesion is measured in the CEUS image(s).

[0103] The method 300 is then performed on the measured dimensions. In step 302a, a consistency check is performed between the CEUS measurement and the B-mode measurement (per step 302 described above). If the two measurements are not within a threshold difference of each other, then in step 304a, the method includes sending a message to the user device so that the user device provides an alert regarding the inconsistency (per step 304 described above). In step 304a, the alert asks the user whether a rescan is desired, and if the user declines, a second alert is generated in step 304b (per step 304) suggesting that the lesion measurement should be repeated.

[0104] The method 300 is then repeated to determine if there are inconsistencies in the diagnosis recorded in the CEUS report. In step 302b, different guidelines are presented to the user for selection for comparison. In step 408, the user provides an indication of the guideline to be used. In step 302c, the attributes of the lesion described in the CEUS report of the CEUS image are compared with the selected medical guideline (used as a reference) to determine inconsistencies in the CEUS report (according to step 302 described above).

[0105] If it is determined that there is no inconsistency, a warning is issued in step 304c (as described above with respect to step 304), asking the user whether any inconsistent fields should be modified. If not, a report is output in step 410.

[0106] Turning now to other embodiments, in another embodiment, a computer program product is provided comprising a computer-readable medium having computer-readable code embodied therein, the computer-readable code being configured to cause the computer or processor to perform one or more of the methods described herein when executed by a suitable computer or processor.

[0107] It will therefore be appreciated that the present disclosure also applies to computer programs, in particular computer programs on or in a carrier, suitable for putting the embodiments into practice. The program may be in the form of source code, object code, a code intermediate between source code and object code (e.g. in partially compiled form), or in any other form suitable for use in implementing the methods according to the embodiments described herein.

[0108] It should also be understood that such a program can have many different architectural designs. For example, the program code implementing the functions of the method or system can be subdivided into one or more subroutines. The various different ways of distributing functions between these subroutines will be apparent to those skilled in the art. The subroutines can be stored together in an executable file to form a self-contained program. Such an executable file may include computer executable instructions, such as processor instructions and / or interpreter instructions (e.g., Java interpreter instructions). Alternatively, one or more or all of the subroutines may be stored in at least one external library file and linked to the main program statically or dynamically (e.g., at runtime). The main program includes at least one call to at least one of the subroutines. The subroutines may also include function calls to each other.

[0109] The carrier of a computer program can be any entity or device capable of carrying the program. For example, the carrier may include a data storage device, such as a ROM (such as a CD-ROM or a semiconductor ROM), or a magnetic recording medium (such as a hard disk). In addition, the carrier may be a transmissible carrier, such as an electrical signal or an optical signal, which may be transmitted via an electric cable or an optical cable or by radio or other means. When the program is implemented in such a signal, the carrier may consist of such a cable or other device or unit. Alternatively, the carrier may be an integrated circuit in which the program is embedded, which is suitable for executing the related method or for use in the implementation of the related method.

[0110] Those skilled in the art can understand and implement variations of the disclosed embodiments when practicing the principles and techniques described herein by studying the drawings, the disclosure, and the claims. In the claims, the word "comprising" does not exclude other elements or steps, and the words "one" or "an" do not exclude multiple. A single processor or other unit can perform the functions of several items described in the claims. The measures described in the mutually different dependent claims can be advantageously combined. The computer program can be stored or distributed on a suitable medium such as an optical storage medium or a solid-state medium provided together with other hardware or as part of other hardware, but can also be distributed in other forms such as via the Internet or other wired or wireless telecommunications systems. Any figure mark in the claims should not be interpreted as limiting the scope.

Claims

1. A computer-implemented method (300) for processing a contrast-enhanced ultrasound image of a lesion, the method comprising: comparing (302) the attributes of the lesion described in the contrast enhanced ultrasound report of the contrast enhanced ultrasound image with a reference, thereby determining inconsistencies in the contrast enhanced ultrasound report; and sending a message to a user device (304) to cause the user device to provide an alert regarding the inconsistency, thereby providing feedback; Wherein, the identified inconsistency includes one of the following: a determined inconsistency between at least two different attributes of the lesion having a predefined relationship, the attributes of the lesion comprising the at least two different attributes of the lesion, the reference comprising the predefined relationship between the at least two different attributes; and a determined inconsistency between the property of the lesion and the reference, the reference comprising the property of the lesion measured in a second ultrasound image acquired using a different modality than the contrast-enhanced ultrasound image.

2. The method (300) according to claim 1, wherein: The attributes of the lesion include contrast phase information from the contrast-enhanced ultrasound report; The reference includes a predefined relationship between different contrast phases according to contrast phase perfusion physiology; and If the contrast phase information from the contrast enhanced ultrasound report is inconsistent with the predefined relationship, an inconsistency is determined.

3. The method (300) of claim 2, wherein: An inconsistency is determined if the contrast phases are not recorded in chronological order or are in a physiologically irrational combination in the contrast-enhanced ultrasound report.

4. The method (300) according to claim 2 or 3, wherein: The predefined relationship between different imaging phases indicates that: The onset of the arterial phase should be before the peak of the contrast medium; If the lesion is isoenhanced during the arterial phase, then the lesion should appear isoenhanced or hypoenhanced during the portal venous phase and / or late phase; If the lesion is isoenhanced during the portal venous phase, the late enhancement should be isoenhanced or hypoenhanced; If the portal venous phase enhancement is isoenhancement, the degree of washout should be none; and / or If the lesion exhibits early washout, the portal venous phase enhancement and late enhancement should only be low, and the degree of washout should be greater than none.

5. The method (300) according to any one of the preceding claims, wherein: The second ultrasound image includes a B-mode image.

6. The method (300) of claim 5, wherein: The property of the lesion described in the contrast-enhanced ultrasound report is a geometric property of the lesion measured in the contrast-enhanced ultrasound image, and the reference is a value of the same geometric property measured in the second ultrasound image; and Wherein, if the value of the geometric property of the lesion measured in the shadow-enhanced ultrasound image differs from the geometric property of the lesion measured in the second ultrasound image by more than a threshold difference, it is determined that the inconsistency exists.

7. The method (300) of claim 6, wherein: The geometric properties include the size, radius, diameter, area or perimeter of the lesion.

8. The method (300) according to any one of the preceding claims, wherein: The reference includes a medical guideline, and the method further includes: obtaining a reference attribute from the medical guideline, wherein the reference attribute is associated with a diagnosis in the contrast-enhanced ultrasound report; and Wherein, for the diagnosis in the ultrasound contrast imaging report, if the attribute in the ultrasound contrast imaging report is incompatible with the reference attribute in the medical guideline, the inconsistency is determined.

9. The method according to claim 8, wherein: The warning indicates that the attribute in the contrast-enhanced ultrasound report is inconsistent with the diagnosis in the contrast-enhanced ultrasound report.

10. The method (300) according to claim 8 or 9, further comprising: receiving user input indicating a particular medical guideline to be used; And wherein the reference attributes are obtained from indicated medical guidelines.

11. The method (300) according to any one of the preceding claims, wherein: The method is performed during a contrast-enhanced ultrasound examination to provide real-time feedback.

12. The method (300) of claim 11, wherein: The warning suggests in real time that a new contrast-enhanced ultrasound scan be performed due to the inconsistency.

13. A device (100) for processing a contrast-enhanced ultrasound image of a lesion, the device comprising: a memory (104) comprising instruction data representing a set of instructions; as well as A processor (102) configured to communicate with the memory and execute the set of instructions, wherein the set of instructions, when executed by the processor, causes the processor to perform the method according to any one of claims 1 to 12.

14. An ultrasound imaging system (200), comprising: The device (100) according to claim 13, and the transducer (6).

15. A computer program product comprising computer readable code configured to, when run by a suitable computer or processor, cause the computer or processor to perform the method according to any one of claims 1 to 12.

Images